Abstract: A computer-implemented method for detecting a target object on a document page that includes detecting a sample target area on a sample document page, generating an image by overlapping a plurality of sample document pages with one another, and detecting one or more cells within the sample target area on the image. The sample target area includes a sample target object. The method further includes extracting one or more informational features from each of the one or more cells. The one or more informational features define characteristics of a corresponding cell of the one or more cells. A machine learning model is trained using the one or more informational features extracted from each of the one or more cells, to detect the sample target object. A target object on a document page is detected using the trained machine learning model.

Abstract: An image based email system associates images with different electronic mail (email) senders. The email system receives email messages from different email senders and then looks through either website member profiles or user contacts for associated images. Any located image is displayed in a list of recent senders. This allows the email user to associate recently received email messages with particular sender images or photographs. The images can also be used in a list of favorite or most frequent email senders. Other features of the email system extract information from received email messages to better identify the email senders. These and other features of the email system provide more intuitive and easier to perform email operations.

Abstract: A method and apparatus for performing simultaneous multi-point measurements of multiple velocity components in a gas flow is described. Pulses of laser light are directed to a measurement region of unseeded gas to produce Rayleigh or Mie scattered light in a plurality of directions. The Rayleigh or Mie scattered light is collected from multiple directions and combined in a single collimated light beam. The Rayleigh or Mie scattered light is then mixed together with a reference laser light before it is passed through a single planar Fabry-Perot interferometer for spectral analysis. At the output of the interferometer, a high-sensitivity CCD camera images the interference fringe pattern. This pattern contains the spectral and spatial information from both the Rayleigh scattered light and the reference laser light. Interferogram processing software extracts and analyzes spectral profiles to determine the velocity components of the gas flow at multiple points in the measurement region.

Abstract: A method and apparatus for performing simultaneous multi-point measurements of multiple velocity components in a gas flow is described. Pulses of laser light are directed to a measurement region of unseeded gas to produce Rayleigh or Mie scattered light in a plurality of directions. The Rayleigh or Mie scattered light is collected from multiple directions and combined in a single collimated light beam. The Rayleigh or Mie scattered light is then mixed together with a reference laser light before it is passed through a single planar Fabry-Perot interferometer for spectral analysis. At the output of the interferometer, a high-sensitivity CCD camera images the interference fringe pattern. This pattern contains the spectral and spatial information from both the Rayleigh scattered light and the reference laser light. Interferogram processing software extracts and analyzes spectral profiles to determine the velocity components of the gas flow at multiple points in the measurement region.